| { | |
| "best_metric": 1.290708303451538, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.028435345134001564, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005687069026800313, | |
| "grad_norm": 0.7424452900886536, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3163, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005687069026800313, | |
| "eval_loss": 1.9984076023101807, | |
| "eval_runtime": 778.1587, | |
| "eval_samples_per_second": 15.223, | |
| "eval_steps_per_second": 1.903, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011374138053600626, | |
| "grad_norm": 1.080130934715271, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6109, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0017061207080400938, | |
| "grad_norm": 1.0433323383331299, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.6837, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002274827610720125, | |
| "grad_norm": 0.8534478545188904, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.5771, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0028435345134001566, | |
| "grad_norm": 0.8350222706794739, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.5236, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0034122414160801876, | |
| "grad_norm": 1.1145470142364502, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.4151, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0039809483187602185, | |
| "grad_norm": 0.8083653450012207, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.3308, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00454965522144025, | |
| "grad_norm": 0.5271626114845276, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.4133, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005118362124120281, | |
| "grad_norm": 0.43272873759269714, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.3583, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005687069026800313, | |
| "grad_norm": 0.4580666124820709, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.382, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006255775929480344, | |
| "grad_norm": 0.4700775146484375, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.3653, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.006824482832160375, | |
| "grad_norm": 0.46370092034339905, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.3269, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007393189734840407, | |
| "grad_norm": 0.32641956210136414, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.2265, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.007961896637520437, | |
| "grad_norm": 0.33604350686073303, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.2166, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.008530603540200469, | |
| "grad_norm": 0.3082321584224701, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.265, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0090993104428805, | |
| "grad_norm": 0.3127622902393341, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.3054, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.009668017345560533, | |
| "grad_norm": 0.31797119975090027, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.3548, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.010236724248240563, | |
| "grad_norm": 0.3794986605644226, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.3261, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.010805431150920594, | |
| "grad_norm": 0.3182049095630646, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.3253, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.011374138053600626, | |
| "grad_norm": 0.33693861961364746, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2528, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011942844956280656, | |
| "grad_norm": 0.37158411741256714, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.3638, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.012511551858960688, | |
| "grad_norm": 0.3820987343788147, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.3177, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01308025876164072, | |
| "grad_norm": 0.35295188426971436, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.3014, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01364896566432075, | |
| "grad_norm": 0.3680730164051056, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.3506, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.014217672567000782, | |
| "grad_norm": 0.3996667265892029, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.4373, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.014217672567000782, | |
| "eval_loss": 1.2989970445632935, | |
| "eval_runtime": 786.3656, | |
| "eval_samples_per_second": 15.064, | |
| "eval_steps_per_second": 1.883, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.014786379469680814, | |
| "grad_norm": 0.2205570936203003, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1953, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.015355086372360844, | |
| "grad_norm": 0.27627643942832947, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.2833, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.015923793275040874, | |
| "grad_norm": 0.2669333815574646, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.2111, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.016492500177720908, | |
| "grad_norm": 0.2802363336086273, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.2611, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.017061207080400938, | |
| "grad_norm": 0.2656974196434021, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.232, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01762991398308097, | |
| "grad_norm": 0.27097079157829285, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.2585, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.018198620885761, | |
| "grad_norm": 0.28322505950927734, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.228, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.01876732778844103, | |
| "grad_norm": 0.28203290700912476, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.2908, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.019336034691121065, | |
| "grad_norm": 0.29397279024124146, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.2699, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.019904741593801095, | |
| "grad_norm": 0.35456985235214233, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.3124, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.020473448496481125, | |
| "grad_norm": 0.3785984218120575, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.3914, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02104215539916116, | |
| "grad_norm": 0.3605644702911377, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.3823, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.02161086230184119, | |
| "grad_norm": 0.22077637910842896, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.1896, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02217956920452122, | |
| "grad_norm": 0.23526205122470856, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.2117, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.022748276107201253, | |
| "grad_norm": 0.3367883563041687, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.357, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.023316983009881283, | |
| "grad_norm": 0.27348804473876953, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.2662, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.023885689912561313, | |
| "grad_norm": 0.25156477093696594, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.2183, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.024454396815241346, | |
| "grad_norm": 0.2880376875400543, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.2991, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.025023103717921377, | |
| "grad_norm": 0.2787708342075348, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2286, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.025591810620601407, | |
| "grad_norm": 0.2973068058490753, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.2677, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02616051752328144, | |
| "grad_norm": 0.3298507332801819, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.3426, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.02672922442596147, | |
| "grad_norm": 0.2946862578392029, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.2525, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0272979313286415, | |
| "grad_norm": 0.3230397701263428, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.3613, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.027866638231321534, | |
| "grad_norm": 0.34295061230659485, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.3333, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.028435345134001564, | |
| "grad_norm": 0.37758418917655945, | |
| "learning_rate": 0.0, | |
| "loss": 1.3443, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.028435345134001564, | |
| "eval_loss": 1.290708303451538, | |
| "eval_runtime": 777.631, | |
| "eval_samples_per_second": 15.233, | |
| "eval_steps_per_second": 1.905, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.070663327724339e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |